Find call sites and references to a symbol across indexed files — with file paths, line numbers, and matching lines. Resolves aliased imports: searching the original name finds call sites that import it under an alias (
AI agents call usages to retrieve information from Local Rag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic code search to locate and display references to symbols within indexed code. It retrieves information about where symbols are used but does not create, modify, delete, execute, or execute code. The operation is purely informational/analytical, making it a Read operation with low severity risk.
From the tool's definition Tool description states it 'Find[s] call sites and references to a symbol across indexed files' and 'Resolves aliased imports'.
Documented attack patterns abuse exactly the kind of access usages gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Local Rag, and nothing reaches the server without passing your rules. This is the rule we recommend for usages:
{
"version": "1",
"default": "deny",
"tools": {
"usages": {}
}
}usages is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find call sites and references to a symbol across indexed files — with file paths, line numbers, and matching lines. Resolves aliased imports: searching the original name finds call sites that import it under an alias (. It is categorised as a Read tool in the Local Rag MCP Server, which means it retrieves data without modifying state.
Register the Local Rag MCP server in PolicyLayer and add a rule for usages: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Local Rag. Nothing to install.
usages is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the usages rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for usages. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
usages is provided by the Local Rag MCP server (thewinci/mimirs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Local Rag, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
29 Local Rag tools catalogued and risk-classified — across an index of 43,000+ MCP servers.